© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5191
    Prev
    Next
    INDEX
    Explanations

    code related to programming constructs and functions in a programming language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    industria
    -0.51
     -
    -0.49
     
    -0.49
    V
    -0.46
     (
    -0.44
    ırlar
    -0.43
     strategis
    -0.43
     –
    -0.43
     Clay
    -0.43
    </u>
    -0.43
    POSITIVE LOGITS
    ########.
    1.82
    :+:
    1.45
    #+#
    1.15
    libft
    1.10
    Datuak
    0.97
    ::::::::
    0.96
     AssemblyProduct
    0.87
    abestanden
    0.85
    ITECH
    0.78
    EndProject
    0.78
    Activations Density 0.035%

    No Known Activations